© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166241
    Prev
    Next
    INDEX
    Explanations

    describes actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seasonal
    0.43
    mor
    0.38
    messenger
    0.38
    delt
    0.38
    mount
    0.38
    esercizio
    0.38
    Seasonal
    0.38
    玹
    0.37
    Gib
    0.37
    rich
    0.37
    POSITIVE LOGITS
     идти
    0.44
     erred
    0.42
    ಗೂ
    0.40
     LANGUAGE
    0.39
     ভাষা
    0.38
    檻
    0.38
    LaunchScheme
    0.38
     cautions
    0.38
     Sprache
    0.37
     भुला
    0.37
    Activations Density 0.000%

    No Known Activations